Updating method of vehicle gear shifting scheme, vehicle, equipment, storage medium and product

Abstract

The invention discloses a vehicle gear shifting scheme updating method, a vehicle, equipment, a storage medium and a product, and belongs to the technical field of vehicles. The method comprises the following steps: acquiring historical data of a vehicle running on a plurality of fixed routes, and identifying working conditions corresponding to each path area in the plurality of fixed routes; generating target vehicle speed change data corresponding to the historical data based on the working condition corresponding to each path area; and the target vehicle speed change data and the vehicle parameters are adopted to update the gear shifting schemes matched with all the fixed routes so that the vehicle can be switched to the matched gear shifting schemes when running according to the different fixed routes. According to the invention, the driving economy of the vehicle driving on each fixed route is optimized.

Description

Technical Field

[0001] This application belongs to the technical field of vehicles, and particularly relates to a method for updating a vehicle shifting scheme, a vehicle, a device, a storage medium, and a product. Background Art

[0002] The shifting scheme of a vehicle has a significant impact on aspects such as the driving economy or power performance of the vehicle. For vehicles with fixed routes, such as buses or logistics vehicles, since their driving routes are relatively stable and predictable, adjusting the shifting scheme according to the fixed routes can improve the vehicle power or driving economy problems caused by the inadaptability of the general scheme to the routes. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems existing in the related art. For this purpose, this application provides a method for updating a vehicle shifting scheme, a vehicle, a device, a storage medium, and a product. By updating the shifting scheme that matches the targeted fixed route, the vehicle can switch to the matching shifting scheme when driving on different fixed routes, improving the vehicle's adaptability to each fixed route and optimizing the driving economy of the vehicle when driving on each fixed route.

[0004] In the first aspect, this application provides a method for updating a vehicle shifting scheme, and the method includes: Obtain the historical data of the vehicle driving on multiple fixed routes, and identify the working conditions corresponding to each passing area in the multiple fixed routes; Based on the working conditions corresponding to each passing area, generate target vehicle speed change data corresponding to the historical data; Use the target vehicle speed change data and vehicle parameters to update the shifting scheme that matches each fixed route respectively, so that the vehicle can switch to the matching shifting scheme when driving on different fixed routes.

[0005] In the above technical solution, by obtaining the historical data of the vehicle driving on multiple fixed routes to identify the working conditions of each passing area of the fixed route, and then generating target vehicle speed change data corresponding to the historical data based on the working conditions of each passing area, the target vehicle speed change data can reflect the historical driving state of the vehicle on this fixed route. Combining with the vehicle parameters that can reflect the vehicle characteristic data, the shifting scheme that matches the targeted fixed route is updated, realizing the solution of the shifting scheme that matches the fixed route according to the historical data of the vehicle. After the shifting scheme that matches the fixed route is updated, the vehicle can shift gears on the fixed route according to the corresponding shifting scheme, which can reduce unnecessary energy loss, improve the vehicle's adaptability to each fixed route, and optimize the driving economy of the vehicle when driving on each fixed route.

[0006] According to some embodiments of the present application, updating the shifting schemes matching each fixed route respectively by using the target vehicle speed change data and vehicle parameters includes: For any fixed curve, establish an energy consumption simulation model with the target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route as the operating condition input and the vehicle parameters as the model parameters; Obtain the default shifting scheme executed by the vehicle under the targeted fixed route, and generate a plurality of candidate shifting schemes that meet the constraints of the vehicle power performance requirements; Based on the default shifting scheme and the plurality of candidate shifting schemes, perform search and update by calling the energy consumption simulation model to obtain the target shifting scheme; Update the shifting scheme matching the targeted fixed route based on the target shifting scheme.

[0007] In the above technical solution, the target vehicle speed change data is used as the operating condition input, an energy consumption simulation model is constructed in combination with the vehicle parameters, and based on the default shifting scheme, a plurality of candidate shifting schemes that meet the constraints of the vehicle power performance requirements are generated. The default shifting scheme and the candidate shifting schemes are sequentially input into the energy consumption simulation model, the vehicle energy consumption under each scheme is calculated, and the target shifting scheme is obtained through search and update, realizing the update of the shifting scheme matching the fixed route. The updated shifting scheme matching the fixed route meets the constraints of the vehicle power performance requirements, enabling the vehicle to shift gears on the fixed route according to the corresponding shifting scheme, and can optimize the driving economy of the vehicle when driving on each fixed route on the premise of meeting the vehicle power performance requirements.

[0008] In a second aspect, the present application provides a method for updating a vehicle shifting scheme, the method including: Before the vehicle travels along a fixed route, detect the current longitude and latitude information of the vehicle; Search for a matching shifting scheme in the shifting scheme index table according to the current longitude and latitude information, and switch to the matching shifting scheme to perform corresponding shifting control; The shifting scheme index table assigns corresponding index values to different fixed routes.

[0009] In the above technical solution, before the vehicle travels along a fixed route, the current longitude and latitude information of the vehicle is detected, and a matching shift plan is searched in the shift plan index table according to the current longitude and latitude information, and the vehicle is switched to the matching shift plan. The shift plan index table contains multiple index values, and each index value corresponds to a fixed route and its matching shift plan. Based on the shift plan index table, the vehicle controller can automatically switch to the matching shift plan according to the current longitude and latitude information of the vehicle, so as to perform corresponding shift control, enable the vehicle to shift gears along the fixed route according to the corresponding shift plan, reduce unnecessary energy loss, improve the adaptability of the vehicle to the fixed route, and optimize the energy consumption performance of the vehicle when traveling along the fixed route.

[0010] In a third aspect, the present application provides a device for updating a vehicle shift plan, the device includes: A data processing unit, configured to obtain historical data of the vehicle traveling on multiple fixed routes, and identify the working conditions corresponding to each passing area in the multiple fixed routes; A vehicle speed data generation unit, configured to generate target vehicle speed change data corresponding to the historical data based on the working conditions corresponding to each passing area; A plan update unit, configured to update the shift plans matching each fixed route respectively by using the target vehicle speed change data and vehicle parameters, so that the vehicle switches to the matching shift plan when traveling along different fixed routes.

[0011] In a fourth aspect, the present application provides a device for updating a vehicle shift plan, the device includes: A detection unit, configured to detect the current longitude and latitude information of the vehicle before the vehicle travels along a fixed route; A switching execution unit, configured to search for a matching shift plan in the shift plan index table according to the current longitude and latitude information, and switch to the matching shift plan to perform corresponding shift control; the shift plan index table assigns corresponding index values to different fixed routes.

[0012] In a fifth aspect, the present application provides a vehicle, including a controller, and the controller is configured to execute the vehicle shift plan update method described in the second aspect above.

[0013] In a sixth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the vehicle shift plan update method described in the first aspect above, or implements the vehicle shift plan update method described in the second aspect above.

[0014] In a seventh aspect, the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method for updating a vehicle shifting scheme as described in the first aspect above, or implements the method for updating a vehicle shifting scheme as described in the second aspect above.

[0015] In an eighth aspect, the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method for updating a vehicle shifting scheme as described in the first aspect above, or implement the method for updating a vehicle shifting scheme as described in the second aspect above.

[0016] In a ninth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the method for updating a vehicle shifting scheme as described in the first aspect above, or implements the method for updating a vehicle shifting scheme as described in the second aspect above.

[0017] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is one of the schematic flowcharts of the method for updating a vehicle shifting scheme provided by some embodiments of the present application; Figure 2 is a schematic diagram of updating a shifting scheme provided by some embodiments of the present application; Figure 3 is another schematic flowchart of the method for updating a vehicle shifting scheme provided by some embodiments of the present application; Figure 4 is yet another schematic flowchart of the method for updating a vehicle shifting scheme provided by some embodiments of the present application; Figure 5 is a schematic flowchart of an improved particle swarm optimization algorithm provided by some embodiments of the present application; Figure 6 is still another schematic flowchart of the method for updating a vehicle shifting scheme provided by some embodiments of the present application; Figure 7 is a schematic diagram of switching a shifting scheme provided by some embodiments of the present application; Figure 8 is one of the schematic structural diagrams of the device for updating a vehicle shifting scheme provided by some embodiments of the present application; Figure 9It is the second structural schematic diagram of the vehicle gear shifting scheme update device provided by some embodiments of the present application; Figure 10 It is the structural schematic diagram of the electronic device provided by some embodiments of the present application. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0020] The terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "and / or" in the description and claims means at least one of the connected objects, and the character " / " generally means an "or" relationship between the associated objects before and after.

[0021] Next, in conjunction with the accompanying drawings, through specific embodiments and their application scenarios, the vehicle gear shifting scheme update method, vehicle, device, storage medium and product provided by the embodiments of the present application will be described in detail.

[0022] The vehicle gear shifting scheme update method provided by the embodiments of the present application, the execution subject of this method can be an electronic device or a functional module or functional entity in the electronic device that can implement the vehicle gear shifting scheme update method. The electronic devices mentioned in the embodiments of the present application include, but are not limited to, Vehicle Control Unit (VCU), Electronic Control Unit (ECU), cloud server, distributed server, and remote vehicle control server, etc. Next, taking the electronic device as the execution subject as an example, the vehicle gear shifting scheme update method provided by the embodiments of the present application will be described.

[0023] Figure 1 It is one of the flow schematic diagrams of the vehicle gear shifting scheme update method provided by some embodiments of the present application. As Figure 1 shown, this method includes: step 110, step 120 and step 130.

[0024] Step 110: Obtain the historical data of the vehicle traveling on multiple fixed routes, and identify the driving conditions corresponding to each passing area in the multiple fixed routes.

[0025] Fixed routes can generally be considered as specific routes with relatively high driving frequencies of vehicles, such as the operating routes of public transportation vehicles or the freight routes of freight vehicles, etc. The driving process of a vehicle on a fixed route usually exhibits certain regularity or repeatability.

[0026] A passing area refers to a segment obtained by dividing a fixed route, and each segment can be called a passing area. The actual geographical features or driving conditions, etc. corresponding to each passing area may vary. For example, the geographical features corresponding to different passing areas of the same fixed route can be urban roads, highways, bridges, or tunnels, etc. In some embodiments, the passing areas in a fixed route are divided based on geographical locations. For example, it can be divided based on longitude and latitude. When the vehicle travels to a certain longitude and latitude according to the fixed route, it is considered that the vehicle enters another passing area from one passing area. The historical data of the vehicle traveling on multiple fixed routes refers to the historical driving data collected during the vehicle's travel on multiple fixed routes. Specifically, the historical data can include, but is not limited to, the vehicle speed, acceleration, accelerator pedal depth, braking frequency, and longitude and latitude during the vehicle's travel on each fixed route, providing a data basis for determining the trajectory characteristics of the vehicle in each passing area based on the historical data.

[0027] In the embodiments of the present application, exemplarily, an electronic device can obtain the historical data of the vehicle traveling on multiple fixed routes from devices such as a vehicle electronic control unit (ECU) or an on-board diagnostics (OBD) system, and can also perform preprocessing after obtaining the historical data to remove outliers and noise in the data. There are various specific ways to identify the driving conditions corresponding to each passing area in the multiple fixed routes based on the historical data of the vehicle traveling on the multiple fixed routes. For example, in some embodiments, by defining a series of rules and thresholds based on driving data such as vehicle speed, acceleration, and throttle opening, different fixed routes and their passing areas are divided into different driving condition types according to the parameter changes in the vehicle driving data; or for example, in some embodiments, after dividing the historical data into multiple data segments, characteristic parameters are calculated for each data segment, and a clustering algorithm is used to perform clustering analysis on the extracted characteristic parameters, so as to label the corresponding driving condition type for each data segment.

[0028] In the embodiments of the present application, the driving conditions corresponding to each route area may be urban road driving conditions, highway driving conditions, congested driving conditions, unobstructed driving conditions, etc. In some embodiments, the speed-time curve of the vehicle driving in the route area can also be used to represent the driving conditions of the route area. The present application does not limit the specific types of driving conditions, which can be set in advance according to actual needs or application scenarios.

[0029] Step 120: Generate target speed change data corresponding to the historical data based on the driving conditions corresponding to each route area.

[0030] It can be understood that the speed change data is data on speed (vehicle speed) and time. For example, it can be represented as a function curve of speed and time (that is, the curve of the vehicle speed changing with time during driving), or it can be a record table of speed, etc., which can reflect the driving state of the vehicle, such as accelerating, decelerating or driving at a constant speed.

[0031] The target speed change data corresponding to the historical data refers to the speed change data generated based on the historical data of the vehicle on a fixed route. The target speed change data reflects the typical driving state of the vehicle on the corresponding fixed route, and the driving state of the vehicle is related to the driving conditions corresponding to each route area. It can also be considered that the target speed change data reflects the types of driving conditions in different route areas of the targeted fixed route.

[0032] In the embodiments of the present application, after identifying the driving conditions corresponding to each route area in multiple fixed routes based on the historical data, the electronic device generates target speed change data corresponding to the historical data based on the driving conditions corresponding to each route area. Exemplarily, key speed data points can be extracted from the historical data, and interpolation algorithms can be used to generate continuous speed change data. For another example, in some embodiments, the historical data can also be analyzed to identify the typical speed patterns of the vehicle under different driving conditions, and combined with the driving condition information of each route area, different typical speed pattern segments can be spliced to generate target speed change data that conforms to the historical data. The generated target speed change data corresponding to the historical data reflects the historical driving state of the vehicle on this fixed route.

[0033] Step 130: Update the gear shifting schemes matched with each fixed route respectively using the target speed change data and vehicle parameters, so that the vehicle switches to the matched gear shifting scheme when driving on different fixed routes.

[0034] It can be understood that the shifting plan is used to guide a vehicle (the shifting mechanism of the vehicle, such as a gearbox) to perform reasonable shifting operations under different working conditions or vehicle speeds. In some embodiments, the shifting plan defines at what vehicle speeds the vehicle should upshift or downshift in each gear under different accelerator pedal depths. In some embodiments, the shifting plan defines contents such as upshift vehicle speed, downshift vehicle speed, and shifting logic. Among them, the upshift vehicle speed refers to the vehicle speed threshold at which the vehicle shifts from the current gear to a higher gear under different accelerator pedal depths; the downshift vehicle speed refers to the vehicle speed threshold at which the vehicle shifts from the current gear to a lower gear under different accelerator pedal depths, and the shifting logic refers to the logic of determining upshifting or downshifting based on data such as the driving state of the vehicle (such as vehicle speed, acceleration, accelerator pedal depth, etc.) and energy consumption requirements.

[0035] The target vehicle speed change data is generated based on the historical data of the vehicle on a fixed route. The historical data includes the actual driving data of the vehicle in different passing areas and different time periods, including vehicle speed, acceleration, driving time, etc. Therefore, the target vehicle speed change data can truly reflect the driving state of the vehicle on this fixed route. In addition, it can also be considered that the target vehicle speed change data implies the working condition information corresponding to each passing area. For example, under urban road conditions, the vehicle speed change data will show frequent acceleration and deceleration and a relatively low average vehicle speed; under highway conditions, the vehicle speed change data shows relatively stable high-speed driving and fewer acceleration and deceleration changes.

[0036] Vehicle parameters refer to various characteristic data that can reflect the driving or power performance of a vehicle, including but not limited to vehicle mass, power and torque characteristics of the motor, transmission ratio of the transmission, rolling resistance coefficient of the tires, and air resistance coefficient. Vehicle parameters affect the power output and energy consumption performance that the vehicle can provide at different vehicle speeds.

[0037] In the embodiments of the present application, the target vehicle speed change data and vehicle parameters are used to update the shifting plan matching the targeted fixed route. Specifically, it can be achieved by optimizing the original shifting plan, or by replacing the original shifting plan with a new shifting plan. Exemplarily, an electronic device can redefine the shifting timing in different vehicle speed intervals in the shifting plan according to the target vehicle speed change data combined with the characteristics of the vehicle power system. By analyzing the driving state of the vehicle in different sections in the target vehicle speed change data, such as acceleration, constant speed, or deceleration stages, the shifting plan is adjusted so that the vehicle can operate in a more optimal gear in each stage. At the same time, combined with vehicle parameters (such as vehicle mass, motor torque, etc.), the required driving force at different vehicle speeds is calculated to optimize the shifting points to reduce unnecessary energy consumption.

[0038] In some embodiments, after combining the updated shifting scheme with the relevant information of the matched fixed route, the electronic device converts it into a data format recognizable by the vehicle (such as the JS key-value pair data (JavaScript Object Notation, JSON) format or the Extensible Markup Language (XML) format, etc.). For example, if the method for updating the vehicle shifting scheme is executed on the server, the shifting scheme data can be sent to the vehicle control unit (such as the Vehicle Control Unit (VCU) or the Electronic Control Unit (ECU) of the vehicle, etc.) through the communication connection between the vehicle and the server.

[0039] The gear shift executed by the vehicle according to the shifting scheme affects the operating efficiency and energy consumption of the vehicle motor. A reasonable shifting scheme adjusts the motor speed and torque of the vehicle through shifting, enabling the motor to operate more in the high-efficiency range, thereby making the motor have better energy consumption performance. Exemplarily, when the vehicle travels along different fixed routes, it switches to the matched shifting scheme. In congested working conditions, the shifting scheme should be able to guide the vehicle to reduce unnecessary shifting operations to adapt to the characteristics of frequent acceleration and deceleration of the vehicle in urban congested conditions and reduce the energy loss of the motor. For another example, in high-speed working conditions, the shifting scheme should be able to be used to guide the vehicle to maintain an appropriate high gear or shift up in a timely manner to reduce the motor speed, thereby reducing energy loss.

[0040] In the embodiments of the present application, by combining the target vehicle speed change data with the vehicle parameters to update the shifting scheme matched with the targeted fixed route, it can be considered that the shifting scheme is updated by combining the historical driving state of the vehicle on the targeted fixed route and the characteristics of the current vehicle. The updated shifting scheme should be able to adapt to the working conditions of the currently targeted fixed route (and each passing area of the fixed route). In some embodiments, the server solves the shifting scheme matched with the fixed route in the simulation environment based on the historical data of the vehicle, and after the shifting scheme is updated and sent to the vehicle, there is no need for real-time route analysis on the vehicle side, avoiding the high computing power requirements for the vehicle and improving the compatibility of vehicle shifting scheme updates. In some embodiments, the shifting scheme matched with each fixed route can also be updated by devices such as the electronic control unit of the vehicle.

[0041] After updating the shifting scheme matched with each fixed route, when the vehicle travels along different fixed routes, it switches to the shifting scheme matched with the fixed route, enabling the vehicle to shift gears reasonably according to the shifting scheme under the current working conditions, reducing unnecessary energy loss, improving the vehicle's adaptability to multiple fixed routes, and optimizing the energy consumption performance of the vehicle when traveling along multiple fixed routes.

[0042] In addition, in the embodiments of the present application, based on the historical data of the vehicle driving on multiple fixed routes and vehicle parameters, the shifting scheme matching each fixed route is updated, and when the vehicle drives on different fixed routes, it switches to the matching shifting scheme, which also realizes the update of the vehicle shifting scheme without relying on high-precision maps (mapless conditions) to a certain extent.

[0043] The method for updating the vehicle shifting scheme provided by the embodiments of the present application obtains the historical data of the vehicle driving on multiple fixed routes to identify the working conditions of each passing area of the fixed route, and then generates target vehicle speed change data corresponding to the historical data based on the working conditions of each passing area. The target vehicle speed change data can reflect the historical driving state of the vehicle on this fixed route. Combining with the vehicle parameters that can reflect the vehicle characteristic data, the shifting scheme matching the targeted fixed route is updated, realizing the solution of the shifting scheme matching the fixed route according to the historical data of the vehicle. After the shifting scheme matching the fixed route is updated, the vehicle can shift gears on the fixed route according to the corresponding shifting scheme, which can reduce unnecessary energy consumption, improve the adaptability of the vehicle to each fixed route, and optimize the driving economy of the vehicle when driving on each fixed route.

[0044] In some embodiments of the present application, the generating of the target vehicle speed change data corresponding to the historical data based on the working conditions corresponding to each passing area includes: For any fixed route, obtain the statistical parameters of the working conditions corresponding to each passing area in the targeted fixed route; Based on the statistical parameters of the working conditions corresponding to each passing area, determine the working condition transition state matrix and the working condition-vehicle speed confusion matrix matching the targeted fixed route; Based on the working condition transition state matrix and the working condition-vehicle speed confusion matrix, generate the target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route.

[0045] The statistical parameters of the working conditions corresponding to each passing area refer to various data obtained by analyzing the historical data of the vehicle in each passing area, which can reflect the characteristics of the working conditions corresponding to each passing area, including but not limited to: the number of occurrences of each working condition, the frequency of each working condition, the duration of each working condition, the statistical characteristics of the vehicle speed under each working condition (such as average vehicle speed, vehicle speed standard deviation, maximum vehicle speed, minimum vehicle speed, etc.), and the number of occurrences of different vehicle speeds under each working condition.

[0046] The working condition transition state matrix is used to represent the probability of a vehicle transitioning between different working conditions on a fixed route. For example, if the working conditions corresponding to each area along a fixed route include three types of working conditions: urban road condition, highway condition, and mountain road condition, the constructed working condition transition state matrix should be a 3×3 working condition state transition matrix, and each element in the matrix represents the probability of transitioning from one working condition to another. For example, the probability of transitioning from the urban road condition to the highway condition is 0.6, etc.

[0047] The working condition - vehicle speed confusion matrix is used to represent the probability of a vehicle having different vehicle speed points under a specific working condition type. For example, for the urban road condition, the constructed vehicle speed confusion matrix may show that the probability of the vehicle speed being 30 km / h is 0.4, and the probability of the vehicle speed being 40 km / h is 0.3, etc.

[0048] In the embodiments of the present application, the electronic device can determine the working condition transition state matrix and the working condition - vehicle speed confusion matrix matching the fixed route in various ways, such as the method based on Markov chain, the method based on machine learning classification algorithm, etc. The present application does not make specific limitations on this.

[0049] The working condition transition state matrix is used to represent the probability of a vehicle transitioning between different working conditions on a fixed route, and the working condition - vehicle speed confusion matrix is used to represent the probability of a vehicle having different vehicle speed points under a specific working condition type. In the embodiments of the present application, the electronic device can generate target vehicle speed change data corresponding to historical data based on these two matrices.

[0050] For example, the target vehicle speed change data can be generated based on the iteration of the time series. The specific process can be starting from the starting point of the fixed route. After initializing the initial working condition and vehicle speed, determine the possible working conditions and their probabilities for the next moment according to the working condition transition state matrix, and according to the determined working condition for the next moment, refer to the working condition - vehicle speed confusion matrix to select the vehicle speed under this working condition. After repeating the above steps, gradually generate the vehicle speed values for subsequent moments, and finally form the complete vehicle speed change data.

[0051] Another example is that the target vehicle speed change data can also be generated based on Markov chain. The specific process can be regarding the vehicle driving process as a Markov chain, using the current working condition as the current state, using the working condition transition state matrix to determine the probability of transitioning to other working conditions in the next step, and after determining the next working condition state, using the working condition - vehicle speed confusion matrix to select a vehicle speed value, repeating this process to simulate the vehicle driving process under different working conditions and generate the vehicle speed change data.

[0052] The generated vehicle speed change data provides detailed and accurate driving state information of the vehicle on the targeted fixed route, which helps to update the shift scheme matching the fixed route according to the vehicle speed change and working condition conversion subsequently.

[0053] The vehicle gear shifting scheme updating method provided by the embodiments of the present application, based on the working condition transition state matrix and the working condition-vehicle speed confusion matrix determined for each path area working condition, respectively represents the transition probability between different working conditions under the targeted fixed route and the probability of the vehicle having different vehicle speed points under a specific working condition. Based on the working condition transition state matrix and the working condition-vehicle speed confusion matrix, target vehicle speed change data corresponding to historical data is generated. The target vehicle speed change data can reflect the historical driving state of the vehicle on this fixed route. Subsequently, by combining the vehicle speed change data with vehicle parameters that can reflect vehicle characteristic data, the gear shifting scheme matching the targeted fixed route can be updated, so that the vehicle can shift gears on the fixed route according to the corresponding gear shifting scheme, thereby optimizing the driving economy of the vehicle when driving on each fixed route.

[0054] In some embodiments of the present application, the determining the working condition transition state matrix and the working condition-vehicle speed confusion matrix matching the targeted fixed route based on the statistical parameters of the working conditions corresponding to each path area includes: According to the sequence of working condition types to which each path area belongs, statistically count the working condition type transition relationship between adjacent path areas to obtain the number of transitions between each working condition type; Based on the number of transitions between each working condition type, construct a working condition transition state matrix; Based on the trajectory data under each working condition type, statistically count the occurrence frequencies of the corresponding vehicle speed values in different intervals to obtain a working condition-vehicle speed confusion matrix matching the targeted fixed route, and the confusion matrix is used to reflect the joint characteristics between the working condition type and the vehicle speed distribution.

[0055] In the embodiments of the present application, according to the sequence of working condition types to which each path area belongs, statistically count the working condition type transition relationship between adjacent path areas. For example, it can be to traverse the working condition type combinations of adjacent path areas one by one according to the sequence of working condition types to which each path area belongs, and statistically count the occurrence frequency of each combination, so as to obtain the number of transitions between each working condition type, providing basic data for constructing the working condition transition state matrix.

[0056] In the embodiments of the present application, after statistically obtaining the number of transitions between each working condition type, construct a working condition transition state matrix. For example, it can be to normalize the number of transitions between each working condition type to a transition probability, and construct a working condition transition state matrix according to the transition probability.

[0057] The following gives an example. Suppose the total number of working condition categories is M, then construct an M×M working condition transition state matrix, and each element in the matrix represents the probability of transitioning from one state (working condition) to another state (working condition). For example, the probability of transitioning from working condition i to working condition j is P(i,j), and the probability calculation method is:

[0058] wherein represents the number of transfers from operating condition i to operating condition j, represents the total number of transfers from operating condition i to other operating conditions.

[0059] In the embodiments of the present application, based on the trajectory data under each operating condition type, the occurrence frequencies of the corresponding vehicle speed values in different intervals are statistically counted, and an operating condition - vehicle speed confusion matrix is constructed accordingly. For example, the vehicle speed values during vehicle driving can be extracted from the trajectory data corresponding to each operating condition type. For each operating condition type, the number of times its vehicle speed falls within each interval is statistically counted, which can be specifically achieved by traversing the vehicle speed values in the trajectory data and performing counting. The statistically obtained frequencies are converted into probabilities, that is, the frequency of each interval is divided by the total number of vehicle speed data points under this operating condition type. The intervals of vehicle speed values can be divided according to actual requirements and application scenarios, and the intervals are multiple consecutive intervals. For example, 0 - 10 km / h, 10 - 20 km / h, etc.

[0060] In some embodiments, the constructed operating condition - vehicle speed confusion matrix has operating condition types as rows and vehicle speed intervals as columns, and the occurrence probabilities calculated above are filled into the corresponding matrix elements, thereby forming an operating condition - vehicle speed confusion matrix. For example, if the probability of vehicle speed a appearing under operating condition category s is B(i, j), then B(i, j) is filled into this matrix element, where the calculation method of B(i, j) can be the same as that of P(i, j).

[0061] The operating condition transfer state matrix intuitively reflects the probability relationship of the conversion between different operating conditions during the vehicle driving on a fixed route. The operating condition - vehicle speed confusion matrix intuitively reflects the occurrence probabilities of vehicle speed values in each interval under different operating condition types, that is, it reflects the relationship between the operating condition type and the vehicle speed distribution, providing a basis for generating target vehicle speed change data corresponding to the historical data of the fixed route subsequently.

[0062] The method for updating the vehicle shifting scheme provided by the embodiments of the present application statistically counts the frequency of the transfer of working condition types between adjacent path regions according to the sequence of working condition types to which each path region belongs, obtains the number of transfers between each working condition type, and constructs a working condition transfer state matrix based on this number. The working condition transfer state matrix intuitively reflects the conversion probability of different working conditions during the vehicle's driving on a fixed route. Based on the trajectory data under each working condition type, the frequency of the vehicle speed appearing in different intervals is statistically counted, and after being converted into probabilities, a working condition-vehicle speed confusion matrix is constructed. The working condition-vehicle speed confusion matrix intuitively reflects the correlation between the working condition type and the vehicle speed distribution, provides data support for generating target vehicle speed change data corresponding to the historical data of the fixed route subsequently, helps the target vehicle speed change data accurately reflect the vehicle driving state, and thus optimizes the energy consumption performance of the vehicle during driving on this fixed route after updating the shifting scheme subsequently.

[0063] In some embodiments of the present application, generating target vehicle speed change data corresponding to the historical data corresponding to the fixed route targeted based on the working condition transfer state matrix and the working condition-vehicle speed confusion matrix includes: Constructing a state transfer path of the working condition sequence according to the working condition transfer state matrix to generate a working condition state sequence fitting the fixed route; Generating corresponding vehicle speed segments according to each working condition type in the working condition state sequence in combination with the corresponding vehicle speed distribution in the working condition-vehicle speed confusion matrix; Splicing multiple vehicle speed segments in the order of the working condition state sequence to obtain target vehicle speed change data corresponding to the historical data corresponding to the fixed route targeted.

[0064] In the embodiments of the present application, constructing a state transfer path of the working condition sequence according to the working condition transfer state matrix. For example, it can be based on the transfer probabilities between each working condition type recorded in the working condition transfer state matrix. Starting from the initial working condition, methods such as the random walk algorithm or Markov chain are used to sequentially determine the working condition types at subsequent moments, thereby gradually constructing the working condition state sequence of the vehicle during the entire driving process on the fixed route (that is, the working condition state sequence fitting the fixed route). For example, within each time step, according to the current working condition and the transfer probability matrix, the next working condition is determined through a random number generator.

[0065] In the embodiments of the present application, generating corresponding vehicle speed segments according to each working condition type in the working condition state sequence in combination with the corresponding vehicle speed distribution in the working condition-vehicle speed confusion matrix. For example, for each working condition type in the working condition state sequence, referring to the occurrence probabilities of each vehicle speed interval under this working condition in the working condition-vehicle speed confusion matrix, vehicle speed values in the corresponding interval are generated through random sampling or according to the probability distribution to generate vehicle speed data within the corresponding time segment.

[0066] After generating the corresponding vehicle speed segments, splice multiple vehicle speed segments in the order of the working condition state sequence to form complete and continuous target vehicle speed change data.

[0067] It can be understood that in the process of generating the target vehicle speed change data corresponding to the historical data, first generate a working condition state sequence that matches the driving characteristics of the fixed route, so that the subsequent generated vehicle speed change data can reflect the working condition changes during the actual driving of the vehicle on the fixed route. Based on the determined working condition sequence, generate a reasonable vehicle speed change for each working condition segment, so that the generated vehicle speed change data also conforms to the characteristics of the historical data in terms of vehicle speed.

[0068] The following gives an example: Start from the starting point of the fixed route and initialize according to the initial working condition (such as urban road working condition) and vehicle speed (for example, 30 km / h) of the fixed route; Divide the driving duration of the vehicle on the fixed route into multiple small time steps, for example, each second as a time step; Within each time step, according to the current working condition and the working condition transition state matrix, calculate the possible working conditions and their probabilities for the next moment. For example, currently in the urban road working condition, there is a 0.6 probability of remaining in the urban road working condition, a 0.3 probability of entering the highway working condition, and a 0.1 probability of entering the mountain road working condition; Randomly determine the actual working condition for the next moment according to the calculated probability of the transferred working condition; According to the determined working condition for the next moment and the vehicle speed probability distribution corresponding to the working condition in the working condition-vehicle speed confusion matrix, randomly select the vehicle speed for the next moment. For example, in the urban road working condition, the probability of the vehicle speed being 40 km / h is 0.4, the probability of 50 km / h is 0.3, and the probability of 60 km / h is 0.2; Starting from the initial moment, continuously repeat the above steps of determining the working condition and vehicle speed, gradually generate the vehicle speed value for each time step until the driving time of the entire fixed route is covered, and finally form the complete target vehicle speed change data.

[0069] In addition, in some embodiments, the method further includes calculating characteristic parameters of the generated vehicle speed change data (such as average vehicle speed, average acceleration, etc.), comparing them with the characteristic parameters in the historical data, and selecting the vehicle speed change data with the lowest absolute error as the final construction result to improve the fitting degree between the generated vehicle speed change data and the historical data, so that the subsequent shift scheme updated according to the vehicle speed change data and matched with the fixed route has a better optimization effect, and the energy consumption performance of the vehicle driving on the fixed route is optimized. The above absolute error can be determined according to the actual application scenario. For example, in some embodiments, the absolute error is that the vehicle speed characteristic error between the vehicle speed change data and the historical data is less than a first threshold, and the mileage error is less than a second threshold.

[0070] The vehicle shift scheme update method provided by the embodiments of the present application constructs a working condition state sequence matching the driving characteristics of the fixed route according to the working condition transfer state matrix, and based on this, generates vehicle speed segments that conform to the actual vehicle speed distribution under each working condition type according to the corresponding vehicle speed distribution in the working condition-vehicle speed confusion matrix, and splices multiple vehicle speed segments in the order of the working condition state sequence to form target vehicle speed change data corresponding to the historical data, providing a basis for the subsequent shift scheme updated according to the vehicle speed change data and matched with the fixed route, and helping to make the subsequent shift scheme updated according to the vehicle speed change data and matched with the fixed route have a better optimization effect, thereby optimizing the energy consumption performance of the vehicle driving on the fixed route.

[0071] In some embodiments of the present application, the updating of the shift scheme matched with each fixed route by using the target vehicle speed change data and vehicle parameters respectively includes: For any fixed curve, an energy consumption simulation model is established with the target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route as the working condition input and the vehicle parameters as the model parameters; Obtain the default shift scheme executed by the vehicle on the targeted fixed route, and generate multiple candidate shift schemes that meet the constraints of the vehicle's dynamic performance requirements; Based on the default shift scheme and multiple candidate shift schemes, search and update by calling the energy consumption simulation model to obtain the target shift scheme; Update the shift scheme matched with the targeted fixed route based on the target shift scheme.

[0072] It can be understood that the energy consumption simulation model can simulate the energy consumption performance of the vehicle when executing different shift schemes on the fixed route. Based on the input target vehicle speed change data, vehicle parameters, etc., it simulates the energy consumption changes during vehicle driving and provides a quantitative evaluation basis for the optimization of the shift scheme.

[0073] The default shifting plan is the shifting strategy currently used by the vehicle on a fixed route. The candidate shifting plans are multiple possible plans generated based on the default plan and meet the constraints of the vehicle's power performance requirements. The default shifting plan and the candidate shifting plans will be jointly used for subsequent search and update to optimize the shifting plan that matches the fixed route. The target shifting plan is the final shifting plan obtained through energy consumption simulation model evaluation and search and update, which can achieve better energy consumption performance while meeting the power performance requirements.

[0074] Among them, the constraints of the vehicle's power performance requirements are the limiting conditions for the vehicle's power performance that need to be met during driving to ensure that the vehicle has sufficient performance. Specifically, the constraints of the vehicle's power performance requirements can include acceleration performance constraints, climbing ability constraints, maximum speed constraints, etc. Among them, the acceleration performance constraint defines the vehicle's ability to accelerate from a standstill to a specific speed, the climbing ability constraint defines the vehicle's driving ability at a specific slope, and the maximum speed constraint defines the maximum speed that the vehicle can achieve.

[0075] For example, in some embodiments, the constraints of the vehicle's power performance requirements include: The upshift speed of each gear should be higher than the maximum upshift speed of the previous gear, the downshift speed should have a certain downshift difference from the upshift speed, the maximum protection speed of the motor, and the limitation of the motor's climbing ability:

[0076]

[0077] Among them, represents the upshift speed when the accelerator pedal opening is Aj% in gear i, represents the downshift speed when the accelerator pedal opening is Aj% in gear i, represents the maximum protection speed of gear i.

[0078] In the embodiments of the present application, using the target vehicle speed change data as the working condition input, an energy consumption simulation model is constructed in combination with vehicle parameters. Exemplarily, an energy consumption simulation model can be built on a simulation platform such as MATLAB, and the vehicle speed change data and parameters are input to simulate vehicle driving and calculate energy consumption. Specifically, constructing the energy consumption simulation model can involve constructing a vehicle dynamics module to simulate the longitudinal and lateral dynamic behaviors of the vehicle, and constructing a vehicle power transmission system module to simulate the output characteristics of the vehicle motor, including the speed-torque curve, efficiency map, etc., so that the energy consumption simulation model can more comprehensively simulate the energy consumption performance of the vehicle when executing different shifting plans on a fixed route. After establishing the energy consumption simulation model, based on the current default shifting plan, multiple candidate shifting plans that meet the constraints of the vehicle's power performance requirements are generated.

[0079] Exemplarily, the electronic device can use algorithms such as the particle swarm optimization algorithm or the genetic algorithm, etc. Based on meeting the vehicle power performance requirements, multiple candidate shift schedules are generated according to the default shift schedule. After generating the candidate shift schedules, the default shift schedule and the candidate shift schedules are input into the energy consumption simulation model in sequence, the vehicle energy consumption under each schedule is calculated, and search and update are performed to obtain the target shift schedule. Taking the generation of candidate schedules by the particle swarm optimization algorithm as an example, through the search mechanism of the particle swarm optimization algorithm, the shift schedule can be iteratively updated according to the energy consumption results, gradually approaching the minimum energy consumption target. Another example, if the genetic algorithm is used to generate candidate schedules, then through operations such as crossover and mutation related to the genetic algorithm, the schedule is continuously iteratively updated until the set number of iterations or fitness threshold is reached, thereby obtaining the target shift schedule. After determining the target shift schedule, the default shift schedule is replaced with the target shift schedule to complete the update of the shift schedule matching the fixed route.

[0080] Figure 2 is a schematic diagram of updating the shift schedule provided by some embodiments of the present application. As Figure 2 shown, in some embodiments, using the target vehicle speed change data and vehicle parameters to update the shift schedule matching each fixed route respectively includes: Importing vehicle model parameters and fixed route condition characteristics (target vehicle speed change data); Taking the original shift curve of the vehicle on the fixed route as the default schedule; Invoking the energy consumption simulation model to simulate the torque execution situation and shift actions of the vehicle under the fixed route condition, and calculating the energy consumption; Invoking the particle swarm optimization algorithm to dynamically adjust the shift schedule and corresponding constraints, and comparing the energy consumption; Performing gradient update on the shift curve, and jumping to the step of invoking the energy consumption simulation model to simulate the torque execution situation and shift actions of the vehicle under the fixed route condition and calculating the energy consumption, and repeating the execution; Outputting the shift curve with the optimal energy consumption per 100 kilometers.

[0081] The method for updating the vehicle shift schedule provided by the embodiments of the present application takes the target vehicle speed change data as the working condition input, constructs an energy consumption simulation model in combination with vehicle parameters, and based on the default shift schedule, generates multiple candidate shift schedules that meet the vehicle power performance requirement constraints. The default shift schedule and the candidate shift schedules are input into the energy consumption simulation model in sequence, the vehicle energy consumption under each schedule is calculated, and the target shift schedule is obtained through search and update, realizing the update of the shift schedule matching the fixed route. The updated shift schedule matching the fixed route meets the vehicle power performance requirement constraints, enabling the vehicle to shift gears according to the corresponding shift schedule on the fixed route, and can optimize the driving economy of the vehicle when driving on each fixed route on the premise of meeting the vehicle power performance requirements.

[0082] In some embodiments of the present application, obtaining the target shifting scheme by searching and updating through calling an energy consumption simulation model based on the default shifting scheme and multiple candidate shifting schemes includes: Represent each shifting scheme in the default shifting scheme and multiple candidate shifting schemes as a particle to obtain an initial particle swarm containing multiple particles; Initialize the initial particle swarm to preliminarily determine the velocity and position of each particle; In each iteration, call the pre-established energy consumption simulation model to calculate the energy consumption of the shifting scheme corresponding to each particle as the fitness value of each particle in the current iteration; Under the constraint of the particle boundary conditions, update the velocity and position of each particle based on the fitness value of each particle in the current iteration; Return to the step of calling the pre-established energy consumption simulation model to calculate the energy consumption of the shifting scheme corresponding to each particle and continue to execute until the iteration termination condition is reached and then stop to obtain the target shifting scheme.

[0083] In the embodiments of the present application, the particle swarm algorithm is improved to realize searching and updating based on the default shifting scheme and multiple candidate shifting schemes through calling an energy consumption simulation model to obtain the target shifting scheme. Specifically, each shifting scheme is represented as a particle. At initialization, the particle swarm consists of the default shifting scheme and multiple randomly generated candidate schemes. The position of each particle represents the specific parameters of the shifting scheme. For example, at a specific accelerator pedal depth, the vehicle speed threshold for the vehicle to shift from the current gear to a higher gear and the vehicle speed threshold for shifting from the current gear to a lower gear. The velocity of the particle represents the step size and direction of the update of the shifting scheme parameters. The magnitude and direction of the velocity affect the speed and path of particle convergence. Excessive velocity may cause the particle to cross the optimal solution, while too small velocity results in slow convergence. The initial position and velocity of the particle can be randomly generated or set within a range based on experience.

[0084] Input each particle (shifting scheme) into the energy consumption simulation model to simulate the energy consumption performance of the vehicle under a fixed route and use this as the fitness value of the particle. Based on this fitness value, adjust the velocity and position of the particle using the update formula of the particle swarm algorithm. At the same time, set particle boundary conditions to ensure that the adjusted shifting scheme parameters remain within a reasonable range and avoid unrealistic schemes, such as the upshift vehicle speed being lower than the lowest vehicle speed of the current gear or the downshift vehicle speed being higher than the highest vehicle speed of the current gear. Through multiple iterations, the particle swarm is continuously updated and gradually approaches the global optimal solution. The iteration termination condition can be reaching the preset maximum number of iterations or the change amount of the fitness value being less than the convergence threshold. The finally obtained target shifting scheme can significantly reduce energy consumption. For example, the energy consumption per 100 kilometers of the shifting scheme is optimized from 15 kWh to 12 kWh, effectively improving the energy consumption performance of the vehicle when driving on each fixed route.

[0085] The vehicle gear - shifting scheme updating method provided by the embodiments of the present application, where each particle represents a gear - shifting scheme, the position and speed of the particle respectively represent the gear - shifting scheme parameters and their updating directions. After the particle swarm initialization is completed, the particles are input into the energy consumption simulation model to calculate the energy consumption as the fitness. The particle position and speed are updated according to the fitness, and the boundaries are constrained to ensure the rationality of the scheme. Iteration is performed until the termination condition is met, and the target gear - shifting scheme with the lowest energy consumption is obtained. The target gear - shifting scheme matches the fixed route it targets. The vehicle shifts gears on the fixed route according to the corresponding gear - shifting scheme, which can reduce unnecessary energy losses, improve the vehicle's adaptability to each fixed route, and optimize the driving economy of the vehicle when driving on each fixed route.

[0086] In some embodiments of the present application, under the constraint of the particle boundary conditions, based on the fitness values of each particle in the current iteration, updating the speed and position of each particle includes: In the current iteration, when the current fitness value of the targeted particle is higher than its own historical individual best fitness value, update the historical individual best fitness value and the corresponding historical individual best position of the targeted particle; Based on the particle with the highest historical individual best fitness value among all particles, update the population best fitness value and the corresponding population best position; According to the speed and position of the targeted particle in the current iteration, the historical individual best position, and the population best position, update the speed of the targeted particle; Calculate the position of the targeted particle in the next iteration based on the updated speed, and correct the position when it exceeds the particle boundary conditions.

[0087] In the embodiments of the present application, during the process of updating the speed and position of each particle, it can be considered that the level of the fitness value directly reflects the quality of the gear - shifting scheme represented by the particle. The lower the energy consumption, the higher the fitness value of the gear - shifting scheme. For example, the energy consumption value calculated by a certain particle through the energy consumption simulation model is 12 kWh per 100 kilometers. Compared with 15 kWh per 100 kilometers of other particles, its fitness value is higher, indicating that the gear - shifting scheme represented by this particle performs better in terms of energy consumption.

[0088] The historical individual best fitness value records the best energy consumption performance of the particle in historical iterations, while the individual best position records the gear - shifting parameters when the particle reaches this best energy consumption. For example, during the iteration process, a particle finds that when the accelerator pedal depth is at a certain level, setting the up - shift vehicle speed to 65 km / h can achieve lower energy consumption, then this setting will be recorded as the individual best position of the particle.

[0089] The global best fitness value and the global best position of the swarm reflect the optimal performance of the entire particle swarm. In each iteration, all the individual best fitness values of the particles are traversed to find the best value and its corresponding gear-shifting parameter, which are used as the global best fitness value and position of the swarm. For example, if the gear-shifting scheme corresponding to the global best fitness value can achieve an energy consumption performance of 12 kWh per 100 kilometers in the simulation, this scheme will be used as a guide to attract other particles to approach it.

[0090] The particle velocity reflects the moving direction and step size of the particle in the solution space. By combining the current velocity of the particle, the individual best position, and the global best position, the velocity update formula can be used to calculate the velocity of the particle in the next iteration. This process not only considers the particle's own optimal historical position but also the global best position of the entire swarm, enabling the particle to find a balance between individual exploration and swarm cooperation. For example, if a particle's current velocity makes it move towards a potentially better solution, while the global best position indicates a better solution in another direction, the velocity update formula of the particle will integrate these two factors to adjust the moving direction and step size of the particle in the hope of finding the global optimal solution.

[0091] The setting of the particle boundary conditions ensures that the position and velocity of the particle remain within a reasonable range, preventing the particle from deviating from the actual feasible solution space during the search process. For example, the upshift vehicle speed cannot be lower than the minimum vehicle speed of the current gear, and the downshift vehicle speed cannot be higher than the maximum vehicle speed of the current gear. In each iteration, after calculating the new position of the particle based on the updated velocity, it is checked whether this position exceeds the particle boundary conditions. If it does, the position of the particle is corrected to within the boundary range to ensure the feasibility of the gear-shifting scheme.

[0092] Under the constraints of the particle boundary conditions, by updating the particle velocity and position based on the fitness value, the particle swarm can continuously approach a better gear-shifting scheme. As the number of iterations increases, the particle swarm gradually approaches the global optimal solution, and the finally obtained gear-shifting scheme can reduce energy consumption while meeting the vehicle's power performance requirements. For example, after multiple iterations of optimization, the energy consumption per 100 kilometers of the gear-shifting scheme is reduced from the initial 15 kWh to 12 kWh, achieving an effective reduction in energy consumption and improving the driving economy of the vehicle.

[0093] In the vehicle gear shifting scheme update method provided by the embodiments of the present application, in each iteration, the current fitness value of the particle is compared with the historical individual best fitness value of the particle itself to update the individual best fitness value and position. And in each iteration, the individual best fitness values of all particles are traversed to find the highest value and its corresponding individual best position, and accordingly, the global best fitness value and the global best position are updated. According to the velocity update formula of the particle swarm algorithm, combining the current velocity of the particle, the individual best position and the global best position, the velocity of the particle in the next iteration is calculated, and the new position of the particle in the next iteration is calculated according to the updated velocity. If the new position exceeds the particle boundary condition, the particle position is corrected back within the boundary range. Through the above steps, the update of the particle velocity and position based on the fitness value is realized under the constraint of the particle boundary condition. This process can guide the particle swarm to continuously approach a better gear shifting scheme and gradually approach the global optimal solution, so as to determine the target gear shifting scheme with the lowest energy consumption and meeting the vehicle power performance requirement constraints after the subsequent iteration ends.

[0094] In some embodiments of the present application, the calling the pre-established energy consumption simulation model to calculate the energy consumption of the gear shifting scheme corresponding to each particle includes: For each particle, according to the gear shifting scheme corresponding to each particle, under the constraint of the gear shifting vehicle speed limit condition, control the vehicle to simulate the execution of the gear shifting scheme corresponding to the particle to be targeted to perform an upshift or downshift operation; Record the number of upshifts and downshifts during the simulation process, and respectively determine the upshift energy consumption corresponding to the upshift operation and the downshift energy consumption corresponding to the downshift operation; Look up the corresponding motor efficiency based on the motor parameters in different gears, and calculate the driving energy consumption during the simulation based on the motor efficiency; Based on the driving energy consumption, the upshift energy consumption and the downshift energy consumption, determine the energy consumption of the gear shifting scheme corresponding to the particle to be targeted.

[0095] The shift speed limit condition refers to the speed range limit that must be followed when the vehicle performs upshifting or downshifting operations during driving. Specifically, the electronic device simulates the vehicle driving process by calling the energy consumption simulation model, and according to the shift plan represented by the particles, controls the vehicle to perform upshifting or downshifting operations in the simulation environment. During the simulation process, each upshift and downshift is recorded to count the number of upshifts and downshifts, and by analyzing the working state of the vehicle power system, the energy consumed by each upshift and downshift operation is calculated. For example, the electronic device can determine the energy consumption of upshifting and downshifting operations by monitoring the torque change and speed change of the vehicle motor and combining the efficiency curve of the motor. According to the operating state of the vehicle in different gears (such as motor speed, torque, etc.), the corresponding motor efficiency is retrieved from the motor performance table. Then, combined with the driving force demand and driving distance of the vehicle, the driving energy consumption during the simulation process is calculated. After comprehensively considering the driving energy consumption, upshift energy consumption, and downshift energy consumption, the total energy consumption of the vehicle under a specific shift plan is obtained.

[0096] The following presents a specific example of calling the pre-established energy consumption simulation model to calculate the energy consumption of the shift plan corresponding to each particle: The energy consumption simulation model is based on the principle of the vehicle longitudinal model and is built on the Simulink simulation platform. The inputs of the model include the working conditions, vehicle model parameters, and motor characteristics, and the output is the energy consumption data of the whole vehicle. The model includes the following key modules: working condition import module, driving force calculation module, shift action simulation module, motor working efficiency query module, and energy consumption calculation module: The working condition import module is used to receive the input vehicle model parameters, vehicle speed curve (target vehicle speed change data), and motor Map parameters; The driving force calculation module is used to calculate the driving force of the whole vehicle according to the vehicle longitudinal model and the motor torque :

[0097]

[0098] Among them, represents the vehicle mass, represents the gravitational acceleration, represents the rolling resistance coefficient, represents the current road slope, represents the air resistance coefficient, is the frontal area, represents the current vehicle speed, represents the inertia coefficient, represents the current acceleration, represents the motor torque, represents the current gear ratio, represents the rolling radius, Indicates the overall vehicle mechanical efficiency Indicates the motor efficiency. The overall vehicle driving force is calculated based on the vehicle mass, gravitational acceleration, rolling resistance coefficient, road gradient, air resistance coefficient, frontal area, current vehicle speed, inertia coefficient, and current acceleration; the motor torque is calculated based on the overall vehicle driving force, current gear ratio, rolling radius, and overall vehicle mechanical efficiency. The above formulas are used to calculate the overall vehicle driving force based on the vehicle operating state and to reverse-calculate the motor output torque in combination with the transmission system parameters.

[0099] The shift action simulation module is used to determine the current vehicle speed , the depth of the accelerator pedal , the current gear rank, and query the current upshift vehicle speed and the downshift vehicle speed . If the current vehicle speed exceeds the upshift vehicle speed, upshift; if the current gear is lower than the downshift vehicle speed, downshift; otherwise, maintain the current gear. The motor working efficiency query module is used to obtain the corresponding motor working efficiency e according to the current motor speed n and the motor torque by looking up a table, and correct the driving force

[0100] It is easy to understand that during the vehicle operation, the driving force Ft required by the overall vehicle is provided by the motor, but there is an efficiency loss in the process of the motor converting electrical energy into mechanical force. Therefore, in order to meet the vehicle's demand for the driving force Ft, the motor actually has to output a larger driving force Ft′, whose magnitude is equal to the driving force required by the vehicle divided by the motor efficiency. Therefore, the above formulas are used to correct the overall vehicle driving force according to the motor efficiency to convert the ideal driving force required for the actual vehicle operation into the actual driving force that the motor needs to provide.

[0101] The energy consumption calculation module is used to introduce a shift energy consumption penalty factor based on the driving energy consumption and calculate the overall vehicle driving energy consumption per 100 kilometers

[0102] In the formula represents the overall vehicle driving force represents the current vehicle speed represents the upshift energy consumption represents the number of upshifts represents the downshift energy consumption Indicates the number of downshifts. It can be understood that the vehicle's driving energy consumption per 100 kilometers is calculated based on the vehicle's driving force, current vehicle speed, vehicle mechanical efficiency, and the energy consumption of shifting operations (including upshift and downshift energy consumption). Specifically, by integrating the change of the product of the vehicle's driving force and vehicle speed over time, the driving energy consumption part is obtained; at the same time, considering the energy consumption of upshift and downshift operations and multiplying them by the corresponding number of shifts respectively, the total shifting energy consumption part is obtained. Adding the driving energy consumption and the shifting energy consumption and dividing by the driving distance (obtained by integrating the ratio of vehicle speed to time) gives the vehicle's driving energy consumption per 100 kilometers.

[0103] The above formula is used to calculate the vehicle's energy consumption per unit distance based on the driving force, motor efficiency, and number of shifts, and can be used to measure the energy consumption performance of a certain shifting scheme under a given vehicle speed curve. It comprehensively considers the power output and shifting impact, and is the basis for evaluating the pros and cons of each group of candidate shifting schemes in the simulation process.

[0104] The method for updating the vehicle shifting scheme provided by the embodiments of the present application, for each particle according to its corresponding shifting scheme, under the constraint of the shifting vehicle speed limit condition, simulates and executes the corresponding shifting operation, and during the simulation process, records the number of upshifts and downshifts to evaluate the impact of the shifting operation on energy consumption. Comprehensively considering the driving energy consumption, upshift energy consumption, and downshift energy consumption, calculates the total energy consumption of the shifting scheme corresponding to the particle, provides a quantitative index for evaluating different shifting schemes, and subsequently uses the energy consumption as the fitness value of each particle in the current iteration, which helps to achieve the goal of determining the shifting scheme with the best energy consumption performance.

[0105] [[ID=​9]]Combined with the above embodiments, the following presents a specific example of obtaining the target shifting scheme through calling the energy consumption simulation model for search and update: (1)Parameter setting Set the particle swarm size to n, the maximum number of iterations to G, the current number of iterations to g, the inertia weight parameter to , ,the acceleration constant to , , , [[ID=2​5]],the convergence accuracy 。

[0106] (2)Population initialization Generate a random initial population containing n particles. Each particle represents a shifting scheme that satisfies the shifting ability constraint, that is, the accelerator pedal opening - vehicle speed matrix of RxA, where R represents the number of upshift lines and downshift lines, and A represents the preset accelerator pedal opening nodes.

[0107] The accelerator pedal opening - vehicle speed matrix can refer to Table 1.

[0108] Table 1 Accelerator pedal opening - vehicle speed matrix

[0109] Among them, represents the upshift vehicle speed at the accelerator pedal opening of Aj% in gear i, represents the downshift vehicle speed at the accelerator pedal opening of Aj% in gear i. Exemplarily, v_u11 represents the upshift vehicle speed at the accelerator pedal opening of A1% in gear 1, and v_d31 represents the downshift vehicle speed at the accelerator pedal opening of A1% in gear 3.

[0110] (3) Particle individual fitness evaluation Import the shift plan, typical working conditions, and vehicle model parameters into the energy consumption simulation model, calculate the fuel consumption per 100 kilometers under the typical working conditions using this shift plan, and use this result as the fitness value of the shift plan, and compare the current plan with the fitness value of the optimal plan in its historical search process fitness value If then is adjusted to the current shift plan, otherwise it remains unchanged. When the iteration number g = 1, = .

[0111] (4) Particle swarm fitness evaluation Compare the optimal fitness of the current plan with the optimal fitness of the particle swarm If the current fitness is better, then is set to the current position of the particle, otherwise it remains unchanged; (5) Particle swarm state update Update the position and velocity vectors of the particles according to the current inertia weight and acceleration constants, and set the iteration number to g + 1:

[0112]

[0113]

[0114]

[0115]

[0116] In the formula, , represent the velocities before and after the particle state update; , represent the positions before and after the particle state update; represents the inertia weight, that is, the degree of inheritance of the particle's movement speed during the iteration process; 、 represents the acceleration constants, which respectively determine the inheritance weights of the particle towards its own optimal position and the global optimal position; 、 are uniformly distributed random numbers within the range of [0, 1]; 、 are the upper and lower limits of the inertia weight. Usually, let = 0.4, = 0.9; 、 、 、 are the upper and lower limits of the acceleration constants. Usually, let = = 2.5, = = 0.5; is the number of iterations; is the maximum number of iterations; is the historical optimal position of particle ; is the global optimal position; is the natural base.

[0117] (6) Particle boundary handling When the particle searches for the optimal position near the boundary, it may cross the boundary due to the influence of random parameters, resulting in an infeasible solution. To confine the particle within the feasible solution space, when the particle's position exceeds the boundary, the position and velocity vector of the particle need to be adjusted according to the following boundary-crossing handling strategy:

[0118]

[0119] In the formula, 、 are the upper and lower limits of the particle search speed, 、 are the upper and lower limits of the shift scheme, is the particle at the iteration, represents the inertia weight, is the particle at

[0120] (7) Termination condition judgment When the number of iterations g If G meets the condition, terminate the algorithm; otherwise, go to (3) Particle individual fitness evaluation to perform fitness evaluation. When the change amount of the fitness value is less than the preset convergence accuracy , terminate the calculation; otherwise, go to (2) Population initialization.

[0121] In some embodiments of the present application, identifying the working conditions corresponding to each passing area in the multiple fixed routes includes: For any fixed route, extract features from the corresponding historical data to obtain the trajectory features of the vehicle in each passing area of the targeted fixed route; Perform clustering analysis on the trajectory features to identify the working conditions corresponding to each passing area.

[0122] The trajectory feature is a characteristic value determined by analyzing and calculating the historical data of vehicle driving, which can reflect the driving state of the vehicle on the passing area of the targeted fixed route. It can be considered that the trajectory feature quantitatively describes the driving state of the vehicle in each passing area, providing a data basis for subsequent clustering analysis to identify the working conditions of the passing area.

[0123] Clustering analysis is usually used to divide the data points in a data set into different clusters, so that the data points within the same cluster have high similarity, while the data points between different clusters have large differences. In the embodiments of the present application, through clustering, the passing areas with similar trajectory features can be grouped into the same working condition type, providing data support for subsequent updating the shift scheme matching the fixed route, enabling the shift scheme to better adapt to different passing areas of each fixed route, thereby improving the driving energy consumption or driving efficiency of the vehicle.

[0124] In the embodiments of the present application, an electronic device can perform clustering analysis on the trajectory features based on the Fuzzy C-Means (FCM) algorithm to identify the working conditions corresponding to each passing area: (1) Initialization: Initialize the membership matrix U and randomly select the initial cluster centers; (2) Assignment step: According to the Euclidean distance, assign each data point to the cluster represented by the nearest centroid; (3) Update step: Update the membership matrix and the cluster centers V; (4) Iteration: Repeat the assignment and update steps until the centroids no longer change significantly or reach the preset number of iterations.

[0125] (5) Result output: Output the working conditions corresponding to each passing area and the associated longitude and latitude.

[0126] The above gives an example of clustering and analyzing trajectory features based on FCM to identify the working conditions corresponding to each route area. The specific method of clustering and analyzing trajectory features to identify the working conditions corresponding to each route area, in addition to the above FCM, can also be the K-Means clustering algorithm, the K-Medoids clustering algorithm, etc. This application does not make specific limitations on this.

[0127] The method for updating the vehicle gear shifting scheme provided by the embodiments of this application extracts features from the historical data corresponding to a fixed route to obtain the trajectory features of each route area of the vehicle in the targeted fixed route, and performs clustering analysis on the trajectory features to realize the identification of the working conditions corresponding to each route area of the fixed route. The working conditions corresponding to each route area can be further used to generate target vehicle speed change data corresponding to the historical data. Subsequently, by combining the vehicle speed change data with the vehicle parameters that can reflect the vehicle characteristic data, the gear shifting scheme matching the targeted fixed route can be updated, so that the vehicle can shift gears according to the corresponding gear shifting scheme on the fixed route, thereby optimizing the driving economy of the vehicle when driving on each fixed route.

[0128] In some embodiments of this application, for any fixed route, extracting features from the corresponding historical data to obtain the trajectory features of each route area of the vehicle in the targeted fixed route includes: For any fixed route, obtain the original data of the vehicle driving according to the targeted fixed route; the original data includes time, vehicle speed, and longitude and latitude information; Perform fragmentation processing on the original data according to the vehicle speed threshold to obtain a plurality of data segments; For each data segment, calculate the multi-dimensional trajectory feature values for describing the vehicle behavior, and perform dimensionality reduction processing on the multi-dimensional trajectory feature values to obtain a plurality of trajectory features; According to the longitude and latitude information of each data segment, determine the route area to which it belongs, and classify the corresponding trajectory features into the route area to which it belongs to form the trajectory features of the vehicle in each route area.

[0129] In some embodiments, the original data of the vehicle is the data of the in-vehicle electrical component (Telematics BOX, T-BOX) in ASC format (the ASC format is a text file format based on the American Standard Code for Information Interchange (ASCII) character set). When the execution subject of the method for updating the vehicle gear shifting scheme is the server, the server can obtain the original data stored locally in the vehicle by sending a data collection instruction to the vehicle.

[0130] It can be considered that not all of the original data of the vehicle is valid. For example, during the driving of the vehicle on a fixed route, it may stop due to abnormal conditions, and the original data under such abnormal conditions cannot effectively represent the actual driving behavior of the vehicle. The trajectory features determined based on the abnormal data cannot reflect the normal driving state of the vehicle in the area passed by on the targeted fixed route.

[0131] Therefore, in the embodiments of the present application, by setting a vehicle speed threshold (for example, set to zero) and extracting continuous data segments with a vehicle speed greater than the vehicle speed threshold, the fragmentation processing and screening of the original data are realized. For each data segment, calculate the multi-dimensional trajectory feature values for describing the vehicle behavior. For example, it can be calculating the average value of all vehicle speed values within the data segment, that is, the total driving distance divided by the total time. It can also be calculating the acceleration by the change in vehicle speed at adjacent time points and then obtaining the average acceleration value. The multi-dimensional trajectory feature values have multiple dimensions, which are obtained based on the analysis and calculation of the historical data of the vehicle driving, including but not limited to running duration, idling duration, acceleration duration, braking duration, constant speed duration, average vehicle speed, average running vehicle speed, maximum vehicle speed, vehicle speed standard deviation, average acceleration, maximum acceleration, acceleration standard deviation, average acceleration pedal depth, acceleration pedal depth standard deviation, average deceleration, maximum deceleration, deceleration standard deviation, average braking depth, braking depth standard deviation. In some embodiments, the types of the trajectory features of the vehicle are set based on relevant working condition classification standards, such as China Automotive Test Cycle (CATC).

[0132] By performing dimensionality reduction processing on the multi-dimensional trajectory feature values and converting these multi-dimensional data into a few principal components, the data structure can be simplified. The trajectory features after dimensionality reduction are easier to process and analyze, removing the redundancy and noise in the multi-dimensional trajectory feature values, which helps to improve the efficiency and accuracy of subsequent clustering analysis.

[0133] After obtaining the trajectory features of each data segment, the data segments need to be classified into the original corresponding passing areas. It can be understood that each data segment actually corresponds to a driving mileage of the vehicle driving on a fixed route. According to the longitude and latitude corresponding to each driving mileage, compare with the longitude and latitude ranges of the pre-divided passing areas to determine the specific passing area to which each data segment belongs. Classifying the trajectory features of each data segment into the corresponding passing areas forms the trajectory features of the vehicle in each passing area, providing a data basis for subsequent clustering analysis of the trajectory features to identify the working conditions corresponding to each passing area.

[0134] In some embodiments, after obtaining the original data of the vehicle driving on the targeted fixed route, the method further includes: performing data cleaning on the original data.

[0135] For example, in some embodiments, the original data is divided by time, and the original data corresponding to a timestamp is taken as an information unit. If there are missing characteristic values such as vehicle speed, time, longitude and latitude in the information unit, or any characteristic value does not match the actual performance parameter range of the vehicle model (such as out of range), then this information unit is excluded.

[0136] In addition, since the original data usually includes multiple characteristics. During the data processing of the original data, it is possible that the data points of some characteristics are not evenly distributed in time, or there are data missing at some time points. For example, the vehicle speed data may be recorded once per second, while the acceleration data may be recorded once every two seconds, or the accelerator pedal depth data at some time points may be missing. Therefore, in some embodiments, based on the time points of the vehicle speed data (vehicle speed time base point), interpolation is performed on the data of other characteristics. Interpolation is a mathematical method used to estimate the value of unknown data points based on known data points. Common interpolation methods include linear interpolation, polynomial interpolation, spline interpolation, etc. By interpolation, the estimated values of other characteristics can be supplemented at each time point of the vehicle speed data, so that the data of all characteristics are aligned on the time axis.

[0137] The vehicle gear shifting scheme updating method provided by the embodiments of the present application obtains the original data of the vehicle driving along the targeted fixed route, performs fragmentation processing on the original data by setting a vehicle speed threshold, screens out the continuous data segments with a vehicle speed greater than the threshold, so as to extract the effective data segments that can represent the actual driving behavior of the vehicle. For each data segment, calculate the multi-dimensional trajectory characteristic values used to describe the vehicle behavior, and perform dimensionality reduction processing on the multi-dimensional trajectory characteristic values to obtain multiple trajectory characteristics, reducing the dimension of the multi-dimensional trajectory characteristic values, removing redundancy and noise in the multi-dimensional trajectory characteristic values, and according to the longitude and latitude information of each data segment, classify the corresponding trajectory characteristics into the route areas to which they belong, and construct the trajectory characteristics of the vehicle in each route area, providing a data basis for subsequent clustering analysis to obtain working conditions and realizing the update of the gear shifting scheme.

[0138] In some embodiments of the present application, the dimensionality reduction processing of the multi-dimensional trajectory characteristic values to obtain multiple trajectory characteristics includes: Performing normalization processing on the multi-dimensional trajectory characteristic values to eliminate the differences in dimension and numerical range of each multi-dimensional trajectory characteristic value; Performing linear transformation on the multi-dimensional trajectory characteristic values by using the principal component analysis method, and extracting multiple principal components covering the main data variation information; Taking the multiple principal components as trajectory characteristics to complete the dimensionality reduction processing of the multi-dimensional trajectory characteristic values.

[0139] It is understandable that multi-dimensional trajectory eigenvalues usually contain different types of data, such as vehicle speed, acceleration, accelerator pedal depth, etc., and their dimensions and value ranges may vary. For example, the vehicle speed is in kilometers per hour, and the acceleration is in meters per second, and the value ranges are quite different.

[0140] The purpose of standardizing multi-dimensional trajectory eigenvalues is to eliminate the above differences in dimensions and value ranges. For example, each eigenvalue in the multi-dimensional trajectory eigenvalues can be linearly transformed to the same scale range (such as [0,1] or [-1,1]). In the embodiments of the present application, the electronic device can standardize the multi-dimensional trajectory eigenvalues by means of maximum-minimum standardization, Z-score standardization, etc. The specific method of standardization in the present application is not limited.

[0141] Principal Component Analysis (PCA) is a statistical analysis method that can be used to transform multiple related variables into a few uncorrelated comprehensive variables (i.e., principal components). The principal components can retain most of the information of the original data while reducing the data dimension.

[0142] It is understandable that linear transformation is an important step in principal component analysis. For example, using the principal component analysis method to perform a linear transformation on multi-dimensional trajectory eigenvalues can be to transform the original multi-dimensional trajectory eigenvalues into a new coordinate system through a specific mathematical method (such as matrix multiplication), eliminating the correlation between the original variables (multi-dimensional trajectory eigenvalues), so that the new variables (principal components) are independent of each other.

[0143] The principal components are linear combinations of the original multi-dimensional trajectory eigenvalues. The principal components are sorted according to the degree of explaining the data variation. The first principal component explains the most variation, and the second principal component explains the most remaining variation under the condition of being orthogonal to the first one, and so on. By extracting multiple principal components that cover the main data variation information and using the principal components as trajectory features, while retaining the key features of the multi-dimensional trajectory eigenvalues, the dimension of the multi-dimensional trajectory eigenvalues can be reduced, and the redundancy and noise in the multi-dimensional trajectory eigenvalues can be removed, which helps to improve the efficiency and accuracy of subsequent clustering analysis.

[0144] In the embodiments of the present application, the electronic device can perform principal component analysis on the multi-dimensional trajectory eigenvalues in the following manner: (1) Calculate the covariance matrix R of the standardized sample values:

[0145] Among them, and are the samples at the and the The values on a feature, and are the means of the and feature respectively, where

[0146] (2) Calculate the eigenvalues and eigenvectors of the covariance matrix R:

[0147] where, are the eigenvalues of the covariance matrix, is the identity matrix.

[0148] The eigenvector corresponding to the eigenvalue is:

[0149] where, .. are the components of the eigenvector respectively.

[0150] (3) Calculate the contribution rate and cumulative contribution rate of the principal components: Contribution rate:

[0151] where, represents the th eigenvalue, represents the sum of all eigenvalues.

[0152] Cumulative contribution rate: (i = 1, 2,..., p) where p is the number of original features, represents the sum of the first eigenvalues, represents the sum of all eigenvalues.

[0153] (4) Interpretation of principal components: Generally, take the first m principal components with a cumulative contribution rate exceeding 80%. The calculation method of the

[0154] th principal component is: is the th principal component, is the component of the

[0155] (5) Data dimensionality reduction: Form an n*m feature matrix (The original data matrix is n*P)

[0156] Among them, are the first m principal components extracted.

[0157] The method for updating the vehicle gear shifting scheme provided by the embodiments of the present application standardizes the multi-dimensional trajectory eigenvalues, eliminates the differences in dimension and numerical range among the eigenvalues, helps to improve the consistency and comparability among the multi-dimensional trajectory eigenvalues, and performs a linear transformation on the standardized data by using the principal component analysis method to extract multiple principal components covering the main data variation information. The principal components are linear combinations of the original eigenvalues. Taking these principal components as the trajectory features, the dimensionality reduction process is completed, realizing the reduction of the dimension of the multi-dimensional trajectory eigenvalues while retaining the key features of the multi-dimensional trajectory eigenvalues, removing the redundancy and noise in the multi-dimensional trajectory eigenvalues, helping to improve the efficiency and accuracy of subsequent clustering analysis. The working conditions obtained by clustering are used for the transfer state matrix and the working condition-vehicle speed confusion matrix, and finally the update of the gear shifting scheme is realized, which helps to improve the effectiveness of the updated gear shifting scheme.

[0158] In some embodiments of the present application, the method further includes: Based on the updated gear shifting scheme, a gear shifting scheme index table for matching different fixed routes is constructed, so that the vehicle continuously obtains the corresponding index value from the gear shifting scheme index table according to the current longitude and latitude information during driving, and executes the matching gear shifting scheme according to the obtained index value; The gear shifting scheme index table contains multiple index values, and each index value corresponds to a fixed route and the gear shifting scheme matched thereto.

[0159] It can be understood that for each fixed route, the matching gear shifting scheme can be updated by the method provided in the above embodiments. In the embodiments of the present application, in the case of multiple fixed routes, the electronic device creates a gear shifting scheme index table, generates a unique index value for each fixed route and its corresponding optimized gear shifting scheme, and stores the index value, the fixed route data, and the corresponding gear shifting scheme in the gear shifting scheme index table. For example, the index value "001" in the gear shifting scheme index table corresponds to the fixed route A and its gear shifting scheme X, and the index value "002" corresponds to the fixed route B and its gear shifting scheme Y.

[0160] If the shift plan index table used to match different fixed routes is built on the server, the server can send the shift plan index table as a command to the vehicle. For example, this can include converting the shift plan index table into a data format acceptable to the vehicle, such as JavaScript Object Notation (JSON) or eXtensible Markup Language (XML), and sending it to the vehicle's Vehicle Control Unit (VCU). The vehicle then stores the index table for easy access during driving. If the shift plan index table is built locally on the vehicle, no sending operation is required.

[0161] While driving, the vehicle can obtain its own latitude and longitude information in real time through positioning devices such as the Beidou Positioning System and the Global Positioning System (GPS), and compare the obtained latitude and longitude information with pre-stored fixed route data to determine the current fixed route. Based on the determined fixed route, the corresponding index value is searched in the index table to obtain a shifting plan that matches the route.

[0162] The method for updating the vehicle shifting scheme provided in the embodiment of the present application constructs a shifting scheme index table including index values, fixed routes and their matching shifting schemes, so that the vehicle can continuously obtain corresponding index values according to current latitude and longitude information during driving, and execute the matching shifting scheme according to the obtained index values, thereby realizing that the vehicle can shift according to the corresponding shifting scheme on each fixed route, which can reduce unnecessary energy loss, improve the vehicle's adaptability to each fixed route, and optimize the vehicle's driving economy on each fixed route.

[0163] Figure 3 This is the second flow chart of the method for updating the vehicle shifting scheme provided by some embodiments of the present application. Figure 2 As shown, the updating method of the vehicle shifting plan further includes: Step 1.1. Classification of working conditions based on short stroke and FCM methods, including: calculating the values of specified characteristic parameters for the divided motion segments, reducing the dimension of the characteristic parameters through principal component analysis, and selecting the principal components with a cumulative contribution rate that meets the requirements as the classification criteria; setting the clustering threshold, using the FCM algorithm to classify the motion segments, and constructing a working condition segment library.

[0164] Step 1.2. Construct a fixed-route driving condition based on the Markov chain, including: dividing the driving states of fixed-route movement segments: constructing a state transition matrix by combining the Kneser-Ney smoothing method; determining the starting state and ending state of the driving condition, and constructing the intermediate transition process using the maximum probability transition principle; calculating the characteristic parameters, duration, and continuous mileage of the driving condition to form a candidate driving condition library.

[0165] Step 1.3. Evaluation of driving conditions based on characteristic parameters, including: comparing the characteristic parameters of the original data segment with the designed driving conditions, calculating the relative mean error, and outputting the designed driving conditions that meet the error threshold.

[0166] Step 2.1. Optimization of the shift curve based on the particle swarm optimization algorithm, including: establishing an energy consumption simulation model to simulate the driving force output, shift action judgment, motor efficiency query, and energy consumption accumulation process during vehicle operation; taking the selected designed driving condition as the background, taking the lowest energy consumption per 100 kilometers as the objective function, and taking the vehicle power demand as the constraint condition, and calling the improved multi-dimensional constrained particle swarm optimization algorithm to optimize the shift curve under typical driving conditions.

[0167] Step 2.2. Switching of the fixed-route shift curve, including: converting the coordinates of the designed driving condition, converting the time axis into a mileage axis, and recording the longitude and latitude information corresponding to each shift curve; designing a fixed-route recognition scheme, where the VCU receives the current vehicle's longitude and latitude information in real time, and combines the heading angle to determine whether the vehicle enters the preset fixed-route area; after entering the fixed-route area and lasting for the corresponding time threshold, switch to the shift scheme corresponding to the current position; continuously monitor the vehicle's operation process, extract and update the fixed-route data, and repeat the process of data rectification, shift scheme optimization, and VCU scheme integration.

[0168] Figure 4 It is the third flow chart of the vehicle shift scheme update method provided by some embodiments of the present application. As Figure 4 shown, the vehicle shift scheme update method further includes: Batch reading of ASC messages; dividing the messages into kinematic segments according to the idle start and end points; calculating the segment characteristic values to form an n*F characteristic matrix, where n is the number of segments and P is the number of characteristics; performing principal component reduction of the characteristic variables; performing FCM clustering analysis; calculating the characteristic values of various typical driving conditions, and merging the typical driving conditions by category; statistically analyzing the state transition matrix according to the working condition type, and statistically analyzing the confusion matrix according to the vehicle speed points that appear in various working conditions, and entering the Markov algorithm; forming a working condition curve that meets the state transition probability, vehicle speed characteristic error <Y%, and mileage error <X m.

[0169] Among them, the principal component reduction of the characteristic variables includes: Feature data standardization; calculate the Pearson correlation coefficient between indicators, and eliminate indicators with a correlation exceeding A%; call the pca principal component analysis function to calculate the contribution rate and indicator coefficients of each principal component; extract the first n principal components with a contribution rate reaching P%; process the feature matrix according to the principal component coefficients after dimensionality reduction.

[0170] Among them, the FCM clustering analysis includes: Set the expected number of classifications N, the distance calculation method as the Euclidean square, and the maximum number of iterations G; initialize the membership matrix U, calculate the initial clustering centers of each category, and iteratively update the membership matrix and clustering centers until the distance between the clustering samples and the clustering centers meets the convergence state; store the kinematic segments by type.

[0171] Figure 5 It is a schematic flow chart of the improved particle swarm algorithm provided by some embodiments of the present application. As Figure 5 shown, the method for updating the vehicle shifting scheme further includes: Particle swarm initialization: Generate an initial population of g particles (g shifting curves), the maximum number of iterations M, the inertia weight w, the self-learning factor and the group learning factor as c1 / c2; Calculation of the fitness value of the initial population particles: Call the simulation model to calculate the fuel consumption per 100 kilometers under all working conditions obtained according to the shifting curve formed by the particle, and use this as the fitness value of the particle, and record the position information of the particle. If the particle corresponds to the historical particle position information library, set the fitness value of the repeated particle to a maximum value to avoid repeated calculation; Optimal scheme update: Traverse the fitness values of each particle in the initial population, and record the particle information corresponding to the minimum fitness value, that is, the shifting curve scheme that minimizes the fuel consumption per 100 kilometers of the whole vehicle; Particle population iteration: Enter the particle swarm iteration process. When the number of iterations is less than M and the calculation result has not converged, mutate the optimal particle information according to the update rule; Boundary processing: Perform boundary processing and determine whether it exists in the historical particle information library. If both conditions are met, calculate and update the optimal particle fitness value and the corresponding position information; Calculation result output: Stop the iteration when the number of iterations reaches the maximum preset number of iterations or the calculation result converges continuously for A times, and output the optimal shifting scheme.

[0172] The method for updating the vehicle shifting scheme provided by the embodiments of the present application is applied to the vehicle controller. That is, the execution subject of this method can be the vehicle controller or a functional module or entity in the vehicle controller that can implement the function of the method for updating the vehicle shifting scheme. The vehicle controller mentioned in the embodiments of the present application includes, but is not limited to, the Vehicle Control Unit (VCU), the Electronic Control Unit (ECU), etc. Hereinafter, taking the vehicle controller as the execution subject as an example, the method for updating the vehicle shifting scheme provided by the embodiments of the present application will be described.

[0173] Figure 6 It is the fourth flow chart of the method for updating the vehicle shifting scheme provided by some embodiments of the present application. As Figure 6 shown, the method for updating the vehicle shifting scheme is applied to the vehicle controller, and the method includes: step 610 and step 620.

[0174] Step 610: Before the vehicle travels along a fixed route, detect the current longitude and latitude information of the vehicle.

[0175] Step 620: Search for a matching shifting scheme in the shifting scheme index table according to the current longitude and latitude information, and switch to the matching shifting scheme to perform corresponding shifting control; The shifting scheme index table assigns corresponding index values to different fixed routes.

[0176] The shifting scheme index table can be generated locally in the vehicle, for example, generated in the vehicle control unit or the vehicle electronic control unit, or can be generated on the server. For example, it is generated by the server according to the original data transmitted back by the vehicle when driving along a fixed route and then sent to the vehicle controller. If the shifting scheme index table is generated on the server, the shifting schemes matching each fixed route can be determined in advance by the server and sent to the vehicle in the form of a shifting scheme index table, without the need for real-time analysis in the vehicle, avoiding the high computing power requirements of the vehicle and improving the compatibility of the update of the vehicle shifting scheme.

[0177] It can be understood that the index table contains multiple index values, and each index value corresponds to a fixed route and its matching shifting scheme. The vehicle controller can search for a matching shifting scheme in the shifting scheme index table according to the current longitude and latitude information.

[0178] For example, the vehicle controller can receive the longitude and latitude data sent by an in-vehicle electrical component (Telematics BOX, T-BOX), so as to monitor the current longitude and latitude information of the vehicle during driving. The T-BOX can obtain its own longitude and latitude information in real time through positioning devices such as the Beidou positioning system and the Global Positioning System (GPS).

[0179] After the vehicle obtains the longitude and latitude information, it can compare the current longitude and latitude information of the vehicle with the pre-stored fixed route data to determine the current fixed route being traveled. According to the determined fixed route, it looks up the corresponding index value in the index table, and then obtains the shift plan matching the route. Executing the corresponding shift control means that the vehicle controller controls the shift mechanism (such as the transmission) of the vehicle according to the shift plan to perform a shift.

[0180] Figure 7 It is a schematic diagram of switching the shift plan provided by some embodiments of the present application. As Figure 7 shown, during the driving process of the vehicle, it continuously detects the shift plan index value (Indx) corresponding to the current longitude and latitude, and dynamically switches the shift plan according to the value of Indx: If Indx = 0, it means that the current longitude and latitude of the vehicle are not in the shift plan index table or the current shift plan is already the shift plan matching the fixed route corresponding to the current longitude and latitude in the shift plan index table. At this time, the shift plan remains unchanged; If Indx = 1, it means that the vehicle is currently driving on the fixed route corresponding to Indx = 1, and the vehicle switches to shift plan 1; If Indx = n, it means that the vehicle is currently driving on the fixed route corresponding to Indx = n, and the vehicle switches to shift plan n.

[0181] The method for updating the vehicle shift plan provided by the embodiments of the present application detects the current longitude and latitude information of the vehicle before the vehicle drives along the fixed route, searches for the matching shift plan in the shift plan index table according to the current longitude and latitude information, and switches to the matching shift plan. The shift plan index table contains multiple index values, and each index value corresponds to a fixed route and its matching shift plan. Based on the shift plan index table, the vehicle controller can automatically switch to the matching shift plan according to the current longitude and latitude information of the vehicle to execute the corresponding shift control, so that the vehicle shifts gears according to the corresponding shift plan on the fixed route, reducing unnecessary energy consumption, improving the adaptability of the vehicle to the fixed route, and optimizing the energy consumption performance of the vehicle during driving on the fixed route.

[0182] The update method for the vehicle shifting scheme provided by the embodiments of the present application may be executed by an update device for the vehicle shifting scheme. In the embodiments of the present application, taking the update device for the vehicle shifting scheme executing the update method for the vehicle shifting scheme as an example, the update device for the vehicle shifting scheme provided by the embodiments of the present application is described.

[0183] Figure 8 It is one of the structural schematic diagrams of the update device for the vehicle shifting scheme provided by some embodiments of the present application. As Figure 8 shown, the update device 800 for the vehicle shifting scheme includes: A data processing unit 801, configured to obtain historical data of the vehicle driving on multiple fixed routes and identify the working conditions corresponding to each passing area in the multiple fixed routes; A vehicle speed data generation unit 802, configured to generate target vehicle speed change data corresponding to the historical data based on the working conditions corresponding to each passing area; A scheme update unit 803, configured to update the shifting schemes matching each fixed route respectively by using the target vehicle speed change data and vehicle parameters, so that when the vehicle drives along different fixed routes, it switches to the matching shifting schemes.

[0184] The update device for the vehicle shifting scheme provided by the embodiments of the present application can implement each process implemented by the above-mentioned update method embodiment of the vehicle shifting scheme. To avoid repetition, it will not be elaborated here.

[0185] The update method for the vehicle shifting scheme applied to the controller of the vehicle provided by the embodiments of the present application may be executed by an update device for the vehicle shifting scheme. In the embodiments of the present application, taking the update device for the vehicle shifting scheme executing the update method for the vehicle shifting scheme applied to the controller of the vehicle as an example, the update device for the vehicle shifting scheme provided by the embodiments of the present application is described.

[0186] Figure 9 It is the second structural schematic diagram of the update device for the vehicle shifting scheme provided by some embodiments of the present application. As Figure 9 shown, the update device 900 for the vehicle shifting scheme includes: A detection unit 901, configured to detect the current longitude and latitude information of the vehicle before the vehicle drives along a fixed route; A switching execution unit 902, configured to search for a matching shifting scheme in the shifting scheme index table according to the current longitude and latitude information and switch to the matching shifting scheme to execute the corresponding shifting control; the shifting scheme index table assigns corresponding index values to different fixed routes.

[0187] The vehicle shift plan update device provided by the embodiments of the present application can implement each process implemented by the vehicle shift plan update method embodiments applied to the controller of the vehicle. To avoid repetition, it will not be elaborated here.

[0188] The vehicle shift plan update device in the embodiments of the present application can be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices other than terminals. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, an in-vehicle electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It can also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0189] The vehicle shift plan update device in the embodiments of the present application can be a device with an operating system. The operating system can be the Microsoft (Windows) operating system, the Android operating system, the IOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0190] The embodiments of the present application also provide a vehicle, including a controller, and the controller is used to execute each process implemented by the vehicle shift plan update method embodiments applied to the controller of the vehicle.

[0191] Figure 10 It is a schematic structural diagram of an electronic device provided by some embodiments of the present application. In some embodiments, as Figure 10 shown, the embodiments of the present application also provide an electronic device 1000, including a processor 1001, a memory 1002, and a computer program stored on the memory 1002 and executable on the processor 1001. When the program is executed by the processor 1001, it implements each process of the vehicle shift plan update method embodiments and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0192] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0193] The embodiments of the present application further provide a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-mentioned embodiment of the method for updating a vehicle shifting scheme, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0194] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disc, etc.

[0195] The embodiments of the present application further provide a computer program product, including a computer program, which implements the above-mentioned method for updating a vehicle shifting scheme when executed by a processor.

[0196] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disc, etc.

[0197] The embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above-mentioned embodiment of the method for updating a vehicle shifting scheme, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0198] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0199] It should be noted that in this text, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0200] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the related technology, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0201] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0202] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0203] Although embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present application. The scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for updating a vehicle shifting scheme, characterized in that The method includes: Obtaining historical data of the vehicle traveling on multiple fixed routes, and identifying the driving conditions corresponding to each passing area in the multiple fixed routes; Generating target vehicle speed change data corresponding to the historical data based on the driving conditions corresponding to each passing area; Using the target vehicle speed change data and vehicle parameters to update the shift schedules matching each fixed route respectively, so that the vehicle switches to the matching shift schedule when traveling on different fixed routes.

2. The method for updating a vehicle gear shifting scheme according to claim 1, wherein The generating target vehicle speed change data corresponding to the historical data based on the driving conditions corresponding to each passing area includes: For any fixed route, obtaining the statistical parameters of the driving conditions corresponding to each passing area in the targeted fixed route; Determining a driving condition transition state matrix and a driving condition - vehicle speed confusion matrix matching the targeted fixed route based on the statistical parameters of the driving conditions corresponding to each passing area; Generating target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route based on the driving condition transition state matrix and the driving condition - vehicle speed confusion matrix.

3. The method for updating a vehicle gear shifting scheme according to claim 2, characterized in that, The determining a driving condition transition state matrix and a driving condition - vehicle speed confusion matrix matching the targeted fixed route based on the statistical parameters of the driving conditions corresponding to each passing area includes: According to the sequence of driving condition types to which each passing area belongs, statistically analyzing the driving condition type transition relationship between adjacent passing areas to obtain the transition times between each driving condition type; Constructing a driving condition transition state matrix based on the transition times between each driving condition type; Based on the trajectory data under each driving condition type, statistically analyzing the occurrence frequencies of the corresponding vehicle speed values in different intervals to obtain a driving condition - vehicle speed confusion matrix matching the targeted fixed route, and the confusion matrix is used to reflect the joint characteristics between the driving condition type and the vehicle speed distribution.

4. The method for updating a vehicle gear shifting scheme according to claim 2 or 3, characterized in that, The generating target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route based on the driving condition transition state matrix and the driving condition - vehicle speed confusion matrix includes: Constructing a state transition path of the driving condition sequence according to the driving condition transition state matrix, and generating a driving condition state sequence fitting the fixed route; Generating corresponding vehicle speed segments according to each driving condition type in the driving condition state sequence, in combination with the vehicle speed distribution corresponding in the driving condition - vehicle speed confusion matrix; Splicing multiple vehicle speed segments in the order of the driving condition state sequence to obtain target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route.

5. The method for updating a vehicle gear shifting scheme according to claim 1, characterized in that, The using the target vehicle speed change data and vehicle parameters to update the shift schedules matching each fixed route respectively includes: For any fixed curve, establishing an energy consumption simulation model with the target vehicle speed change data corresponding to the historical data corresponding to the targeted fixed route as the driving condition input and the vehicle parameters as the model parameters; Obtaining the default shift schedule executed by the vehicle under the targeted fixed route, and generating multiple candidate shift schedules meeting the constraints of the vehicle's power performance requirements; Based on the default shift schedule and multiple candidate shift schedules, performing search and update by calling the energy consumption simulation model to obtain the target shift schedule. Update the shifting plan that matches the targeted fixed route based on the targeted shifting plan.

6. The method for updating a vehicle gear shifting scheme according to claim 5, characterized in that, Based on the default shifting plan and multiple candidate shifting plans, search and update through calling an energy consumption simulation model to obtain a targeted shifting plan, including: Represent each shifting plan in the default shifting plan and multiple candidate shifting plans as a particle to obtain an initial particle swarm containing multiple particles; Initialize the initial particle swarm to preliminarily determine the velocity and position of each particle; In each iteration, call a pre-established energy consumption simulation model to calculate the energy consumption of the shifting plan corresponding to each particle as the fitness value of each particle in the current iteration; Under the constraint of the particle boundary conditions, update the velocity and position of each particle based on the fitness value of each particle in the current iteration; Return to the step of calling the pre-established energy consumption simulation model to calculate the energy consumption of the shifting plan corresponding to each particle and continue to execute until the iteration termination condition is reached and then stop to obtain the targeted shifting plan.

7. The method for updating a vehicle gear shifting scheme according to claim 6, wherein The updating the velocity and position of each particle based on the fitness value of each particle in the current iteration under the constraint of the particle boundary conditions includes: In the current iteration, when the current fitness value of the targeted particle is higher than its own historical individual best fitness value, update the historical individual best fitness value and the corresponding historical individual best position of the targeted particle; Based on the particle with the highest historical individual best fitness value among all particles, update the population best fitness value and the corresponding population best position; Update the velocity of the targeted particle according to the velocity and position of the targeted particle in the current iteration, the historical individual best position, and the population best position; Calculate the position of the targeted particle in the next iteration based on the updated velocity and correct the position when it exceeds the particle boundary conditions.

8. The method for updating a vehicle gear shifting scheme according to claim 6 or 7, characterized in that, The calling the pre-established energy consumption simulation model to calculate the energy consumption of the shifting plan corresponding to each particle includes: For each particle, according to the shifting plan corresponding to each particle, under the constraint of the shifting vehicle speed limit condition, control the vehicle to simulate the execution of the shifting plan corresponding to the targeted particle to perform upshifting or downshifting operations; Record the number of upshifts and downshifts during the simulation process, and respectively determine the upshift energy consumption corresponding to the upshifting operation and the downshift energy consumption corresponding to the downshifting operation; Look up the corresponding motor efficiency based on the motor parameters at different gears and calculate the driving energy consumption during the simulation based on the motor efficiency; Based on the driving energy consumption, upshift energy consumption, and downshift energy consumption, determine the energy consumption of the shifting plan corresponding to the targeted particle.

9. The method for updating a vehicle gear shifting scheme according to claim 1, wherein The identifying the working conditions corresponding to each passing area in the multiple fixed routes includes: For any fixed route, perform feature extraction on the corresponding historical data to obtain the trajectory features of the vehicle in each passing area in the targeted fixed route; Perform clustering analysis on the trajectory features to identify the working conditions corresponding to each passing area.

10. The method for updating a vehicle gear shifting scheme according to claim 9, characterized in that, The performing feature extraction on the corresponding historical data for any fixed route to obtain the trajectory features of the vehicle in each passing area in the targeted fixed route includes: For any fixed route, obtain the original data of the vehicle driving along the targeted fixed route; the original data includes time, vehicle speed, and longitude and latitude information; Perform fragmentation processing on the original data according to the vehicle speed threshold to obtain a plurality of data segments; For each data segment, calculate the multi-dimensional trajectory feature values for describing the vehicle behavior, and perform dimensionality reduction processing on the multi-dimensional trajectory feature values to obtain a plurality of trajectory features; According to the longitude and latitude information of each data segment, determine the area it passes through, and classify the corresponding trajectory features into the area it passes through to form the trajectory features of the vehicle in each area it passes through.

11. The method for updating a vehicle gear shifting scheme according to claim 10, wherein The dimensionality reduction processing of the multi-dimensional trajectory feature values to obtain a plurality of trajectory features includes: Perform normalization processing on the multi-dimensional trajectory feature values to eliminate the differences in dimension and numerical range of each multi-dimensional trajectory feature value; Adopt the principal component analysis method to perform linear transformation on the multi-dimensional trajectory feature values, and extract a plurality of principal components covering the main data variation information; Use the plurality of principal components as trajectory features to complete the dimensionality reduction processing of the multi-dimensional trajectory feature values.

12. The method for updating the vehicle gear shifting scheme according to claim 1, characterized in that, The method further includes: Based on the updated shift plan, construct a shift plan index table for matching different fixed routes, so that the vehicle continuously obtains the corresponding index value from the shift plan index table according to the current longitude and latitude information during driving, and executes the matching shift plan according to the obtained index value; The shift plan index table contains a plurality of index values, and each index value corresponds to a fixed route and its matching shift plan.

13. A method for updating a vehicle gear shifting scheme, characterized in that, Applied to the vehicle controller, the method includes: Before the vehicle drives along a fixed route, detect the current longitude and latitude information of the vehicle; Find the matching shift plan in the shift plan index table according to the current longitude and latitude information, and switch to the matching shift plan to execute the corresponding shift control; The shift plan index table assigns corresponding index values to different fixed routes.

14. A vehicle, characterized in that, Including a controller, the controller is used to execute the vehicle shift plan update method as described in claim 13.

15. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the vehicle shift plan update method as described in any one of claims 1-12, or executes the vehicle shift plan update method as described in claim 13.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle shift plan update method as described in any one of claims 1-12, or executes the vehicle shift plan update method as described in claim 13.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle shift plan update method as described in any one of claims 1-12, or executes the vehicle shift plan update method as described in claim 13.

Images